Title: Feature binding pulse-coupled neural network model using a double colour space

Authors: Hongxia Deng; Han Li; Sha Chang; Jie Xu; Haifang Li

Addresses: School of Computer Science and Technology, Taiyuan University of Technology, No. 209, Daxue Road, Yuci District, Jinzhong City, Shanxi Prov., China ' School of Computer Science and Technology, Taiyuan University of Technology, No. 209, Daxue Road, Yuci District, Jinzhong City, Shanxi Prov., China ' School of Computer Science and Technology, Taiyuan University of Technology, No. 209, Daxue Road, Yuci District, Jinzhong City, Shanxi Prov., China ' School of Computer Science and Technology, Taiyuan University of Technology, No. 209, Daxue Road, Yuci District, Jinzhong City, Shanxi Prov., China ' School of Computer Science and Technology, Taiyuan University of Technology, No. 209, Daxue Road, Yuci District, Jinzhong City, Shanxi Prov., China

Abstract: The feature binding problem is one of the central issues in cognitive science and neuroscience. To implement a bundled identification of colour and shape for a colour image, a double-space vector feature binding PCNN (DVFB-PCNN) model was proposed based on the traditional pulse-coupled neural network (PCNN). In this model, the method of combining RGB colour space with HSI colour space successfully solved the problem that all colours cannot always be separated completely. Through the use of the first pulse emission time of the neurons, the different characteristics were successfully separated. Through the colour sequence produced by this process, the different characteristics belonging to the same perceived object were bound together. Experiments showed that the model can successfully achieve separation and binding of image features and will be a valuable tool for PCNN in the feature binding of colour images.

Keywords: feature binding; cognitive science; neuroscience; colour; shape; double-spaces; pulse-coupled neural network; RGB colour space; HSI colour space; pulse emission time; colour sequence.

DOI: 10.1504/IJCSE.2018.090487

International Journal of Computational Science and Engineering, 2018 Vol.16 No.2, pp.141 - 152

Received: 26 Jun 2016
Accepted: 18 Jan 2017
Published online: 19 Mar 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article